Research map / Architectures and efficiency / Neural architecture search
EC-DARTS: Inducing Equalized and Consistent Optimization Into DARTS
Qinqin Zhou, Xiawu Zheng, Liujuan Cao, Bineng Zhong, Teng Xi, Gang Zhang, Errui Ding, Mingliang Xu, Rongrong Ji
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Cross-Edge Normalization (CEN) (ablation) | DARTS · CIFAR10 | test error (%): 2.76 -> 2.60 | Improved |
| add Induced Structural Transition (IST) (ablation) | DARTS · CIFAR10 | test error (%): 2.76 -> 2.47 | Improved |
| add IST on top of CEN (ablation) | DARTS + CEN · CIFAR10 | test error (%): 2.60 -> 2.39 | Improved |
| add CEN on top of IST (ablation) | DARTS + IST · CIFAR10 | test error (%): 2.47 -> 2.39 | Improved |
| add CEN (ablation) | DARTS · CIFAR10 architectures (10 edge combinations) | Kendall Tau (operation weight vs performance): 0.06 -> 0.63 | Improved |
| add IST (ablation) | DARTS · single search, 10 sampled architectures | Kendall Tau (search rank vs retraining rank): 0.13 -> 0.47 | Improved |
| use EC-DARTS instead of DARTS | DARTS · 10 independent searches on CIFAR10 | average retraining accuracy (%): 97.13% -> 97.61% | Improved |
| add CEN (ablation) | DARTS · CIFAR10 | search cost | No clear effect |
| search on target dataset instead of transferring from CIFAR10 | EC-DARTS · Tiny-ImageNet-200 | test error (%): 28.7 -> 28.1 | Improved |
| search on target dataset instead of transferring from CIFAR10 | EC-DARTS · ImageNet | top-1 error (%): 24.3 -> 23.6 | Improved |
| search on CIFAR100 instead of transferring from CIFAR10 | EC-DARTS · CIFAR100 | test error (%): 16.13 -> 15.72 | Improved |
| search on CIFAR100 instead of CIFAR10 | EC-DARTS · CIFAR10 | test error (%): 2.39 -> 2.44 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DARTS+ — DARTS-: Robustly Stepping out of Performance Collapse Without Indicators (ICLR 2021) · better on 2 of 2 shared results
- FairDARTS — Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search (ECCV 2020) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search (ICLR 2020 · similarity 0.91)
- $\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells (ICLR 2023 · similarity 0.91)
- Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search (ECCV 2020 · similarity 0.91)
- iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients (ICML 2021 · similarity 0.90)
- IS-DARTS: Stabilizing DARTS through Precise Measurement on Candidate Importance (AAAI 2024 · similarity 0.88)
- EG-NAS: Neural Architecture Search with Fast Evolutionary Exploration (AAAI 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
